tae 🔸

Karma: 345

tae 🔸Aug 27, 2023, 8:36 PM
11 points
1 ∶ 0
on: How much do EAGs cost (and why)?
How about reducing the number of catered meals while increasing support for meals outside the venue? Silly example: someone could fill a hotel room with Soylent so that everyone can grab liquid meals and go chat somewhere—sort of a “baguettes and hummus” vibe. Or as @Matt_Sharp pointed out, we could reserve nearby restaurants. No idea if these exact plans are feasible, but I can imagine similarly scrappy solutions going well if planned by actual logistics experts.

Thanks so much for your work and this information!

tae 🔸Apr 21, 2023, 6:09 PM
39 points
0 ∶ 0
on: All AGI Safety questions welcome (especially basic ones) [April 2023]
I’m having an ongoing discussion with a couple professors and a PhD candidate in AI about “The Alignment Problem from a Deep Learning Perspective” by @richard_ngo, @Lawrence Chan, and @SoerenMind. They are skeptical of “3.2 Planning Towards Internally-Represented Goals,” “3.3 Learning Misaligned Goals,” and “4.2 Goals Which Motivate Power-Seeking Would Be Reinforced During Training”. Here’s my understanding of some of their questions:
1. The argument for power-seeking during deployment depends on the model being able to detect the change from the training to deployment distribution. Wouldn’t this require keeping track of the distribution thus far, which would require memory of some sort, which is very difficult to implement in the SSL+RLHF paradigm?
2. What is the status of the model after the SSL stage of training?
  1. How robust could its goals be?
  2. Would a model be able to know:
    what misbehavior during RLHF fine-tuning would look like?
    that it would be able to better achieve its goals by avoiding misbehavior during fine-tuning?
  3. Why would a model want to preserve its weights? (Sure, instrumental convergence and all, but what’s the exact mechanism here?)
3. To what extent would all these phenomena (situationally-aware reward hacking, misaligned internally-represented goals, and power-seeking behaviors) show up in current LLMs (say, GPT-4) vs. current agentic LLM-based systems (say, AutoGPT) vs. different future systems?
  1. Do we get any evidence for these arguments from the fact that existing LLMs can adopt goal-directed personas?

tae 🔸Jan 4, 2023, 10:49 PM
6 points
0 ∶ 0
on: Bill Burr on Boiling Lobsters (also manliness and AW)
I’m guessing this has been discussed in the animal welfare movement somewhere
Yep, The Sexual Politics of Meat by Carol J. Adams is the classic I’m aware of.

tae 🔸Aug 27, 2022, 11:06 PM
4 points
0 ∶ 0
on: Driving Education on EA Topics Through Khan Academy
General information about people in low-HDI countries to humanize them in the eyes of the viewer.

Similar for animals (except not “humanizing” per se!). Spreading awareness that e.g. pigs act like dogs may be a strong catalyst for caring about animal welfare. Would need to consult an animal welfare activism expert.

My premise here: it is valuable for EAs to viscerally care about others (in addition to cleverly working toward a future that sounds neat).

tae 🔸Aug 22, 2022, 7:55 PM
2 points
0 ∶ 0
in reply to: nongiga’s comment on: “Call off the EAs”: Too Much Advertising?
Yes, I am pretty amused about this

tae 🔸Aug 20, 2022, 11:38 PM
16 points
0 ∶ 0
in reply to: Marcel D’s comment on: “Call off the EAs”: Too Much Advertising?
I’ll just continue my anecdote! As it happens, the #1 concern that my friend has about EA is that EAs work sinisterly hard to convince people to accept the narrow-minded longtermist agenda. So, the frequency of ads itself increases his skepticism of the integrity of the movement. (Another manifestation of this pattern is that many AI safety researchers see AI ethics researchers as straight-up wrong about what matters in the broader field of AI, and therefore need to be convinced rather than collaborated with.)
(Edit: the above paragraph is an anecdote, and I’m speaking generally in the following paragraphs)

I think it is quite fair for someone with EA tendencies, who is just hearing of EA for the first time through these ads, to form a skeptical first impression of a group that invests heavily in selling an unintuitive worldview.

I strongly agree that it’s a good sign if a person investigates such things instead of writing them off immediately, indicating a willingness to take unusual ideas seriously. However, the mental habit of openness/curiosity is also unusual and is often developed through EA involvement; we can’t expect everyone to come in with full-fledged EA virtues.

tae 🔸Aug 20, 2022, 2:38 AM
14 points
0 ∶ 0
in reply to: abier’s comment on: “Call off the EAs”: Too Much Advertising?
Sure! Thank you very much for your, ahem, forethought about this complicated task. Please pardon the naive post about a topic that you all have worked hard on already :)

tae 🔸Jun 4, 2022, 7:14 AM
1 point
0 ∶ 0
on: Responsible/fair AI vs. beneficial/safe AI?

tae 🔸Jun 3, 2022, 12:06 AM
3 points
0 ∶ 0
in reply to: Charles He’s comment on: Guided by the Beauty of One’s Philosophies: Why Aesthetics Matter
Thanks very much, that helps!
Adding more not to defend myself, but to keep the conversation going:
I think that many Enlightenment ideas are great and valid regardless of their creators’ typical-for-their-time ideas.
Education increasingly includes rather radical components of critical race theory. Students are taught that if someone is racist, then all of their political and philosophical views are tainted. By extension, many people learn that the Enlightenment itself is tainted. Like Charles, I think that this “produces misguided perspectives”.
I’m—apparently badly—trying to communicate the following. These students, who have been taught that the Enlightenment is tainted by association with racism, who (reasonably!) haven’t bothered to thoroughly research this particular historical movement to come to their own conclusions, who may totally make great EAs, would initially be turned off.
It’s quite plausible that it shouldn’t be the case that Enlightenment aesthetics might turn people off. But I think this is the case, and I argue that it’s likely more important to make a good first impression than to take a stand in favor of a particular historical movement.
Hope that makes sense!

tae 🔸Jun 2, 2022, 7:40 PM
1 point
0 ∶ 0
in reply to: tae 🔸’s comment on: Guided by the Beauty of One’s Philosophies: Why Aesthetics Matter

tae 🔸May 20, 2022, 7:34 AM
−1 points
0 ∶ 0
in reply to: tae 🔸’s comment on: Guided by the Beauty of One’s Philosophies: Why Aesthetics Matter
Short version: if we can avoid it, let’s not filter potential EAs by the warmth of their feelings toward a specific group of historical figures (especially because history education is inevitably biased)

tae 🔸May 20, 2022, 7:20 AM
2 points
0 ∶ 0
in reply to: Arjun Panickssery’s comment on: Guided by the Beauty of One’s Philosophies: Why Aesthetics Matter
I actually wouldn’t know where to find a liberal student who respects classics (let alone “our cultural heritage”) at my large American university, after four years in the philosophy department!

tae 🔸May 20, 2022, 7:16 AM
0 points
0 ∶ 0
in reply to: Larks’s comment on: Guided by the Beauty of One’s Philosophies: Why Aesthetics Matter
Yes, these are great reasons to take inspiration from the Enlightenment!

The point I most want to get across is that, by using Enlightenment aesthetics, EAs could needlessly open themselves up to negative perception.
1. If EAs use Enlightenment aesthetics more, then EA will be associated with the Enlightenment more.
2. Regardless of their positive qualities, Enlightenment philosophers racked up plenty of negative qualities among them. Maybe there were 10x as many purely virtuous ones as problematic ones; maybe every problematic one made contributions that vastly outweighed their issues; nonetheless, there are some problems.
3. People who would otherwise engage with EA might have heard of enough problems that they’d be put off by Enlightenment associations entirely. (I suspect many of my social-justice-y friends would have this reaction.)
Here’s the more nebulous point. I hinted in my original comment that I take issue with the “rational individualistic actor” view. This alone puts me off Enlightenment aesthetics, because I think that particular view is especially dangerous considering how innocent it looks. But that’s a whole big discussion, and I respect the other side! The relevant part here is just that, anecdotally, at least one EA isn’t a huge Enlightenment fan.

tae 🔸May 18, 2022, 8:08 PM
1 point
0 ∶ 0
in reply to: Arjun Panickssery’s comment on: Guided by the Beauty of One’s Philosophies: Why Aesthetics Matter
Yeah, the magnitude of the problem depends on the empirical question of how many people associate the Enlightenment with racism and such.

Descartes’ moral circle issue is that he believed animals have no moral standing whatsoever, so he enthusiastically practiced vivisection (dissecting animals while they were still alive).

tae 🔸May 18, 2022, 6:20 PM
−5 points
0 ∶ 0
in reply to: Arjun Panickssery’s comment on: Guided by the Beauty of One’s Philosophies: Why Aesthetics Matter
We’d need to be really careful.
The Enlightenment led to good foundational ideas of EA, but it was also full of philosophers who conceptualized humans as individualistic rational actors, excluded pretty much everybody except for white men from the moral circle, and advocated for constant growth with no regard for sustainability (e.g. Immanuel Kant, Rene Descartes, Adam Smith).

I do think historical aesthetics are great (see my other comment on this post), but I think we should stick to historical art that isn’t so closely tied to questionable philosophy.
EDIT: I see how this came across differently than I intended! I do not mean that we should cancel the Enlightenment. Please see child comments for explanation.

tae 🔸May 18, 2022, 6:10 PM
6 points
0 ∶ 0
on: Guided by the Beauty of One’s Philosophies: Why Aesthetics Matter
I’m more inspired by the “altruistic” aesthetic than the “effective” aesthetic.
“Effective” blends into the Silicon Valley productivity/efficiency crowd. While there’s a lot to appreciate about the Bay Area, I’d prefer not to tie EA to that culture.
On the other hand, there are truly beautiful exemplars of altruism throughout history and around the world.
Personally, I associate altruism with Avalokiteśvara. Art portraying him is colorful and full of details, which, to me, represents that Effective Altruism can bridge all kinds of cultures, theories, and life experiences. Here’s why he has so many heads and arms:
One prominent Buddhist story tells of Avalokiteśvara vowing never to rest until he had freed all sentient beings from saṃsāra. Despite strenuous effort, he realizes that many unhappy beings were yet to be saved. After struggling to comprehend the needs of so many, his head splits into eleven pieces. Amitābha, seeing his plight, gives him eleven heads with which to hear the cries of the suffering. Upon hearing these cries and comprehending them, Avalokiteśvara tries to reach out to all those who needed aid, but found that his two arms shattered into pieces. Once more, Amitābha comes to his aid and invests him with a thousand arms with which to aid the suffering multitudes.^[34]
I’m gonna need help coming up with more examples of historical altruistic art… Civil rights art from the US? (I love this painting of Harriet Tubman reaching out to the viewer.) Some Christian saints?

tae 🔸May 17, 2022, 8:20 PM
17 points
0 ∶ 0
on: Try to sell me on [ EA idea ] if I’m [ person with a viewpoint ]

tae 🔸Apr 13, 2022, 9:09 PM
28 points
0 ∶ 0
in reply to: Jan-Willem’s comment on: Free-spending EA might be a big problem for optics and epistemics
Adding on: Increasing EA spending in certain areas could certainly support diversity, but it could have the opposite effect elsewhere.

I’m concerned that focusing community-building efforts at elite universities only increases inequality. I’m guessing that university groups do much of the recruiting for all-expenses-paid activities. In practice, then, students at elite universities will benefit, while students at state schools and community colleges won’t even hear about these opportunities. So the current EA community-building system quite accurately selects for privileged students to give money to.

Curious about any work to change this pattern!

tae 🔸Mar 23, 2022, 11:54 PM
7 points
0 ∶ 0
on: Let Russians go abroad
Thanks for the great idea!
Here’s an email script summarizing this article. I wrote it in ~5 minutes to send to my US Congressional representative, so it’s not very polished, but I think it’s good enough.
Hi! I’d like to encourage Rep. ___ to advocate for opening borders to Russians as much as possible. Any simplification of the visa process will help. This will weaken Russia and its onslaught on Ukraine while also strengthening our economy.
First, Russian men who don’t want to fight would avoid conscription or desert the army by immigrating to the US with their families. Second, the Russian economy would weaken: emigrants would stop paying taxes, and the Russian military would experience brain drain. Third, a kind welcome from the US would weaken Putin’s propaganda that everyone hates Russian people.
As for us, we’d get the best kind of immigrants: people willing to change their lives to avoid supporting a corrupt government. These people are the most likely to have savings, higher education, in-demand skills, English skills, and generally a good grip on reality.
In conclusion, let’s welcome Russian people to take a stand against the Russian government!

tae 🔸Mar 23, 2022, 5:34 PM
2 points
0 ∶ 0
on: What are academic disciplines, movements or organisations that you think EA should try to learn more from?
“Strong Towns is an international movement dedicated to making communities across the United States and Canada financially strong and resilient.” Advocates for friendly human-scale dense cities over car-centric suburbia. I learned about Strong Towns through the similarly educational YouTube channel Not Just Bikes.
Of course, this is relevant to global development work. And I feel better qualified to vote/advocate for local urban planning.
Finally, from a rationalist perspective, it was fascinating to watch my mind change as I understood how my American surroundings were built for cars, not people.